TUDataset: A collection of benchmark datasets for learning with graphs

Abstract

Recently, there has been an increasing interest in (supervised) learning with graph data, especially using graph neural networks. However, the development of meaningful benchmark datasets and standardized evaluation procedures is lagging, consequently hindering advancements in this area. To address this, we introduce the TUDataset for graph classification and regression. The collection consists of over 120 datasets of varying sizes from a wide range of applications. We provide Python-based data loaders, kernel and graph neural network baseline implementations, and evaluation tools. Here, we give an overview of the datasets, standardized evaluation procedures, and provide baseline experiments. All datasets are available at www.graphlearning.io. The experiments are fully reproducible from the code available at www.github.com/chrsmrrs/tudataset.

arXiv commentICML 2020 workshop "Graph Representation Learning and Beyond"

References in corpus (16)

• Inductive Representation Learning on Large Graphs
• Neural Message Passing for Quantum Chemistry
• Graph Neural Networks: A Review of Methods and Applications
• Fast Graph Representation Learning with PyTorch Geometric
• What's in a crowd? Analysis of face-to-face behavioral networks
• Open Graph Benchmark: Datasets for Machine Learning on Graphs
• A Survey on Graph Kernels
• Benchmarking Graph Neural Networks
• A Fair Comparison of Graph Neural Networks for Graph Classification
• The Multiscale Laplacian Graph Kernel
• Machine Learning on Graphs: A Model and Comprehensive Taxonomy
• Alchemy: A Quantum Chemistry Dataset for Benchmarking AI Models
• Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification
• GraKeL: A Graph Kernel Library in Python
• Recognizing Cuneiform Signs Using Graph Based Methods
• IPC: A Benchmark Data Set for Learning with Graph-Structured Data

Cited by in corpus (68)

• Graph Contrastive Learning with Augmentations
• SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentation
• Causal Attention for Interpretable and Generalizable Graph Classification
• Adversarial Graph Augmentation to Improve Graph Contrastive Learning
• OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs
• Understanding Pooling in Graph Neural Networks
• A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability
• Accurate Learning of Graph Representations with Graph Multiset Pooling
• Graph Signal Processing and Deep Learning: Convolution, Pooling, and Topology
• Federated Graph Classification over Non-IID Graphs
• Graph Kernels: State-of-the-Art and Future Challenges
• DIG: A Turnkey Library for Diving into Graph Deep Learning Research
• Rethinking pooling in graph neural networks
• Graph Pooling via Coarsened Graph Infomax
• Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks
• Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentations
• Contrastive Learning with Hard Negative Samples
• Higher-order Clustering and Pooling for Graph Neural Networks
• GraphWorld: Fake Graphs Bring Real Insights for GNNs
• Cell Attention Networks
• Projective Ranking-based GNN Evasion Attacks
• Edge Representation Learning with Hypergraphs
• A Meta-Learning Approach for Graph Representation Learning in Multi-Task Settings
• Explainability-based Backdoor Attacks Against Graph Neural Networks
• Large-scale graph representation learning with very deep GNNs and self-supervision
• Supervised Contrastive Learning with Hard Negative Samples
• ADOM: Accelerated Decentralized Optimization Method for Time-Varying Networks
• From Local Structures to Size Generalization in Graph Neural Networks
• How Framelets Enhance Graph Neural Networks
• Size-Invariant Graph Representations for Graph Classification Extrapolations
• LimeSoDa: A Dataset Collection for Benchmarking of Machine Learning Regressors in Digital Soil Mapping
• Adversarial Attacks on Graph Classification via Bayesian Optimisation
• Weisfeiler and Lehman Go Paths: Learning Topological Features via Path Complexes
• LCS Graph Kernel Based on Wasserstein Distance in Longest Common Subsequence Metric Space
• Ranking Structured Objects with Graph Neural Networks
• Hyperparameter-free and Explainable Whole Graph Embedding
• Generalizing Downsampling from Regular Data to Graphs
• Boosting Multitask Learning on Graphs through Higher-Order Task Affinities
• Reconstruction for Powerful Graph Representations
• An Empirical Study of Graph Contrastive Learning
• Learning to Pool in Graph Neural Networks for Extrapolation
• Local, global and scale-dependent node roles
• XInsight: Revealing Model Insights for GNNs with Flow-based Explanations
• Learnable Structural Semantic Readout for Graph Classification
• Learning Graphons via Structured Gromov-Wasserstein Barycenters
• Watermarking Graph Neural Networks based on Backdoor Attacks
• A Hard Label Black-box Adversarial Attack Against Graph Neural Networks
• Quantum evolution kernel : Machine learning on graphs with programmable arrays of qubits
• Embedding Graphs on Grassmann Manifold
• Should Graph Neural Networks Use Features, Edges, Or Both?
• Hard Negative Sampling via Regularized Optimal Transport for Contrastive Representation Learning
• CGCL: Collaborative Graph Contrastive Learning without Handcrafted Graph Data Augmentations
• Partition and Code: learning how to compress graphs
• Fea2Fea: Exploring Structural Feature Correlations via Graph Neural Networks
• Multi-Level Attention Pooling for Graph Neural Networks: Unifying Graph Representations with Multiple Localities
• Topological Graph Neural Networks
• Weisfeiler and Leman go Hyperbolic: Learning Distance Preserving Node Representations
• Data-Driven Self-Supervised Graph Representation Learning
• Improving the Expressive Power of Graph Neural Network with Tinhofer Algorithm
• How Faithful are Self-Explainable GNNs?
• Learning Graphon Autoencoders for Generative Graph Modeling
• Graph2Graph Learning with Conditional Autoregressive Models
• Edge but not Least: Cross-View Graph Pooling
• Towards a Taxonomy of Graph Learning Datasets
• Learning on Random Balls is Sufficient for Estimating (Some) Graph Parameters
• Graph embedding using multi-layer adjacent point merging model
• Diversified Multiscale Graph Learning with Graph Self-Correction
• Scaling up graph homomorphism for classification via sampling